[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-71965":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":23,"hasPages":25,"topics":26,"createdAt":10,"pushedAt":10,"updatedAt":46,"readmeContent":47,"aiSummary":48,"trendingCount":16,"starSnapshotCount":16,"syncStatus":49,"lastSyncTime":50,"discoverSource":51},71965,"voice-pro","abus-aikorea\u002Fvoice-pro","abus-aikorea","Gradio WebUI for creators and developers, featuring key TTS (Edge-TTS, kokoro) and zero-shot Voice Cloning (E2 & F5-TTS, CosyVoice), with Whisper audio processing, YouTube download, Demucs vocal isolation, and multilingual translation.","https:\u002F\u002Fwww.wctokyoseoul.com",null,"Python",10869,1585,65,36,0,373,430,1422,1119,44.6,"GNU General Public License v3.0",false,"main",true,[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45],"audiobook","faster-whisper","gradio","karaoke","podcasts","speech-recognition","speech-synthesis","speech-to-text","subtitles","text-to-speech","transcription","translator","tts","voice-cloning","voice-conversion","webui","whisper","whisperx","yt-dlp","2026-06-12 02:02:56","\u003C!-- \n    title: Voice-Pro: Ultimate AI Voice Conversion and Multilingual Translation Tool\n    description: Powerful AI-powered web application for YouTube video processing, speech recognition, translation, and text-to-speech with multilingual support\n    keywords: AI voice conversion, YouTube translation, subtitle generation, speech-to-text, text-to-speech, voice cloning, multilingual translation, ElevenLabs Alternative \n    author: ABUS\n    version: 2.0.0\n    last-updated: 2025-02-23\n    product-type: AI Multimedia Processing Software\n    platforms: Windows\n    technology-stack: Whisper, Edge-TTS, Gradio, CUDA, Faster-Whisper, Whisper-Timestamped, WhisperX, E2-TTS, F5-TTS, YouTube Downloader, Demucs, MDX-Net, RVC, CosyVoice, kokoro\n    license: LGPL\n-->\n\n\n\n\u003Ch1 align=\"center\">\nVoice-Pro\n\u003C\u002Fh1>\n\n\u003Cp align=\"center\">\n  \u003Ci align=\"center\">The best AI speech recognition, translation, and multilingual dubbing solution 🚀\u003C\u002Fi>\n\u003C\u002Fp>\n\n\u003Ch4 align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fdeepwiki.com\u002Fabus-aikorea\u002Fvoice-pro\">\n    \u003Cimg alt=\"Ask DeepWiki.com\" src=\"https:\u002F\u002Fdeepwiki.com\u002Fbadge.svg\" style=\"height: 20px;\">\n  \u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fwww.youtube.com\u002Fchannel\u002FUCbCBWXuVbk-OBp9T4H5JjAA\">\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fyoutube-d95652.svg?style=flat-square&logo=youtube\" alt=\"youtube\" style=\"height: 20px;\">\n  \u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fwww.buymeacoffee.com\u002Fabus\">\n    \u003Cimg src=\"https:\u002F\u002Fwww.buymeacoffee.com\u002Fassets\u002Fimg\u002Fcustom_images\u002Forange_img.png\" alt=\"Buy Me a Coffee\" style=\"height: 20px;\">\n  \u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fabus-aikorea\u002Fvoice-pro\u002Freleases\">\n    \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fv\u002Frelease\u002Fabus-aikorea\u002Fvoice-pro\" alt=\"release\" style=\"height: 20px;\">\n  \u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fabus-aikorea\u002Fvoice-pro\u002Fstargazers\">\n    \u003Cimg alt=\"GitHub Repo stars\" src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fabus-aikorea\u002Fvoice-pro\">\n  \u003C\u002Fa>  \n\u003C\u002Fh4>\n\n\u003Cp align=\"center\">\n    \u003Cimg src=\"docs\u002Fimages\u002Fmain_page_crop.eng.jpg?raw=true\" alt=\"Dubbing Studio\"\u002F>\n\u003C\u002Fp>\n\u003Cbr \u002F>\n\n\n\n## 🎙️ An AI-powered web application for speech recognition, translation, and dubbing\n\n\n\u003Cp>  \n  \u003Ca href=\"docs\u002FREADME.kor.md\">\n    \u003Cimg src=\"https:\u002F\u002Fflagcdn.com\u002F16x12\u002Fkr.png\" alt=\"South Korea Flag\" style=\"vertical-align: middle;\"> 한국어\n  \u003C\u002Fa> ∙ \n  \u003Ca href=\"docs\u002FREADME.eng.md\">\n    \u003Cimg src=\"https:\u002F\u002Fflagcdn.com\u002F16x12\u002Fus.png\" alt=\"United Kingdom Flag\" style=\"vertical-align: middle;\"> English\n  \u003C\u002Fa> ∙ \n  \u003Ca href=\"docs\u002FREADME.zh.md\">\n    \u003Cimg src=\"https:\u002F\u002Fflagcdn.com\u002F16x12\u002Fcn.png\" alt=\"China Flag\" style=\"vertical-align: middle;\"> 中文简体\n  \u003C\u002Fa> ∙ \n  \u003Ca href=\"docs\u002FREADME.tw.md\">\n    \u003Cimg src=\"https:\u002F\u002Fflagcdn.com\u002F16x12\u002Ftw.png\" alt=\"Taiwan Flag\" style=\"vertical-align: middle;\"> 中文繁體\n  \u003C\u002Fa> ∙ \n  \u003Ca href=\"docs\u002FREADME.jpn.md\">\n    \u003Cimg src=\"https:\u002F\u002Fflagcdn.com\u002F16x12\u002Fjp.png\" alt=\"Japan Flag\" style=\"vertical-align: middle;\"> 日本語\n  \u003C\u002Fa> ∙ \n  \u003Ca href=\"docs\u002FREADME.deu.md\">\n    \u003Cimg src=\"https:\u002F\u002Fflagcdn.com\u002F16x12\u002Fde.png\" alt=\"Germany Flag\" style=\"vertical-align: middle;\"> Deutsch\n  \u003C\u002Fa> ∙ \n  \u003Ca href=\"docs\u002FREADME.spa.md\">\n    \u003Cimg src=\"https:\u002F\u002Fflagcdn.com\u002F16x12\u002Fes.png\" alt=\"Spain Flag\" style=\"vertical-align: middle;\"> Español\n  \u003C\u002Fa> ∙ \n  \u003Ca href=\"docs\u002FREADME.por.md\">\n    \u003Cimg src=\"https:\u002F\u002Fflagcdn.com\u002F16x12\u002Fpt.png\" alt=\"Portugal Flag\" style=\"vertical-align: middle;\"> Português\n  \u003C\u002Fa>\n\u003C\u002Fp>\n\nVoice-Pro is a state-of-the-art web app that transforms multimedia content creation. It integrates YouTube video downloading, voice separation, speech recognition, translation, and text-to-speech into a single, powerful tool for creators, researchers, and multilingual professionals.\n- 🔊 Top-tier speech recognition: **Whisper**, **Faster-Whisper**, **Whisper-Timestamped**, **WhisperX**\n- 🎤 Zero-shot voice cloning: **F5-TTS**, **E2-TTS**, **CosyVoice**\n- 📢 Multilingual text-to-speech: **Edge-TTS**, **kokoro** (Paid version includes **Azure TTS**)\n- 🎥 YouTube processing & audio extraction: **yt-dlp**\n- 🌍 Instant translation for 100+ languages: **Deep-Translator** (Paid version includes **Azure Translator**)\n\n\nA robust alternative to **ElevenLabs**, Voice-Pro empowers podcasters, developers, and creators with advanced voice solutions.\n\n## ⚠️ Please Note\n- Due to [WeConnect](https:\u002F\u002Fwww.wctokyoseoul.com) development work, Voice-Pro development and updates are not possible for the time being.\n- We have made all Voice-Pro code open source and completely free. Voice-Pro can now be freely distributed and modified by anyone.\n- It works well on Windows with NVIDIA GPU. Operation on Mac and Linux has not been verified.\n- Please leave your requests on the [![GitHub Issues](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fissues\u002Fabus-aikorea\u002Fvoice-pro)](https:\u002F\u002Fgithub.com\u002Fabus-aikorea\u002Fvoice-pro\u002Fissues)  or  [![GitHub Discussions](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fdiscussions\u002Fabus-aikorea\u002Fvoice-pro)](https:\u002F\u002Fgithub.com\u002Fabus-aikorea\u002Fvoice-pro\u002Fdiscussions) pages.\n- **Troubleshooting**: In most cases, issues can be resolved by deleting the `installer_files` folder and then running `configure.bat` followed by `start.bat`.\n\n\n## 📰 News & History\n\n\u003Cdetails open>\n\u003Csummary>version 3.2\u003C\u002Fsummary>\n\n- We have been focusing on [WeConnect](https:\u002F\u002Fwww.wctokyoseoul.com) development for the past few months and have not been able to manage Voice-Pro at all. \n- We have decided to open source all Voice-Pro code.\n- Voice-Pro is completely free and supports Windows, Mac, Linux.\n- [WeConnect](https:\u002F\u002Fwww.wctokyoseoul.com) is an application for global cultural exchange.\n- Connect with people from all over the world for meaningful cultural exchanges, language learning, and international friendships.\n\n\u003Cp align=\"center\">\n    \u003Cimg src=\"docs\u002Fimages\u002FHotpot 0.png?raw=true\" alt=\"ScreenShot 0\" width=\"18%\"\u002F>\n    \u003Cimg src=\"docs\u002Fimages\u002FHotpot 1.png?raw=true\" alt=\"ScreenShot 1\" width=\"18%\"\u002F>\n    \u003Cimg src=\"docs\u002Fimages\u002FHotpot 2.png?raw=true\" alt=\"ScreenShot 2\" width=\"18%\"\u002F>\n    \u003Cimg src=\"docs\u002Fimages\u002FHotpot 3.png?raw=true\" alt=\"ScreenShot 3\" width=\"18%\"\u002F>\n    \u003Cimg src=\"docs\u002Fimages\u002FHotpot 4.png?raw=true\" alt=\"ScreenShot 4\" width=\"18%\"\u002F>\n\u003C\u002Fp>\n\n\u003C\u002Fdetails>\n\n\n\u003Cdetails>\n\u003Csummary>version 3.1\u003C\u002Fsummary>\n\n- 🪄 Support for fine-tuned models of **F5-TTS**\n- 🌍 Supported languages\n  - \u003Cimg src=\"https:\u002F\u002Fflagcdn.com\u002F16x12\u002Fus.png\" alt=\"United Kingdom Flag\" style=\"vertical-align: middle;\"> English & \u003Cimg src=\"https:\u002F\u002Fflagcdn.com\u002F16x12\u002Fcn.png\" alt=\"China Flag\" style=\"vertical-align: middle;\"> Chinese: \u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002FSWivid\u002FF5-TTS\u002Ftree\u002Fmain\u002FF5TTS_v1_Base\"> SWivid\u002FF5-TTS_v1 \u003C\u002Fa> \n  - \u003Cimg src=\"https:\u002F\u002Fflagcdn.com\u002F16x12\u002Ffi.png\" alt=\"Spain Flag\" style=\"vertical-align: middle;\"> Finnish: \u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002FAsmoKoskinen\u002FF5-TTS_Finnish_Model\"> AsmoKoskinen\u002FF5-TTS_Finnish_Model \u003C\u002Fa> \n  - \u003Cimg src=\"https:\u002F\u002Fflagcdn.com\u002F16x12\u002Ffr.png\" alt=\"Spain Flag\" style=\"vertical-align: middle;\"> French: \u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002FRASPIAUDIO\u002FF5-French-MixedSpeakers-reduced\"> RASPIAUDIO\u002FF5-French-MixedSpeakers-reduced \u003C\u002Fa> \n  - \u003Cimg src=\"https:\u002F\u002Fflagcdn.com\u002F16x12\u002Fin.png\" alt=\"Spain Flag\" style=\"vertical-align: middle;\"> Hindi: \u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002FSPRINGLab\u002FF5-Hindi-24KHz\"> SPRINGLab\u002FF5-Hindi-24KHz \u003C\u002Fa>  \n  - \u003Cimg src=\"https:\u002F\u002Fflagcdn.com\u002F16x12\u002Fit.png\" alt=\"Spain Flag\" style=\"vertical-align: middle;\"> Italian: \u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Falien79\u002FF5-TTS-italian\"> alien79\u002FF5-TTS-italian \u003C\u002Fa>  \n  - \u003Cimg src=\"https:\u002F\u002Fflagcdn.com\u002F16x12\u002Fjp.png\" alt=\"Spain Flag\" style=\"vertical-align: middle;\"> Japanese: \u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002FJmica\u002FF5TTS\u002Ftree\u002Fmain\u002FJA_21999120\"> Jmica\u002FF5TTS\u002FJA_21999120 \u003C\u002Fa>  \n  - \u003Cimg src=\"https:\u002F\u002Fflagcdn.com\u002F16x12\u002Fru.png\" alt=\"Spain Flag\" style=\"vertical-align: middle;\"> Russian: \u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fhotstone228\u002FF5-TTS-Russian\"> hotstone228\u002FF5-TTS-Russian \u003C\u002Fa> \n  - \u003Cimg src=\"https:\u002F\u002Fflagcdn.com\u002F16x12\u002Fes.png\" alt=\"Spain Flag\" style=\"vertical-align: middle;\"> Spanish: \u003Ca href=\"https:\u002F\u002Fhuggingface.co\u002Fjpgallegoar\u002FF5-Spanish\"> jpgallegoar\u002FF5-Spanish \u003C\u002Fa> \n  \n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>version 3.0\u003C\u002Fsummary>\n\n- 🔥 Removed the **AI Cover** feature.  \n- 🚀 Added support for **m-bain\u002FwhisperX**.\n  \n\u003C\u002Fdetails>\n\n\u003Cdetails>\n\u003Csummary>version 2.0\u003C\u002Fsummary>\n\n- 🐍 Built with Python 3.10.15, Torch 2.5.1+cu124, and Gradio 5.14.0.  \n- 🆓 Free trial supports media up to **60 seconds** in length.  \n- 🔥 Added the **AI Cover** feature.  \n- 🎤 Introduced support for **CosyVoice** and **kokoro**.  \n- ⏳ Initial run downloads **CozyVoice2-0.5B (9GB)**, which may take over an hour depending on network speed.  \n- 🎧 Voice samples for cloning will be continuously updated.  \n- 📝 Added **spaCy** for natural sentence-by-sentence translation and TTS.  \n- ☁️ Subscription version includes **Microsoft Azure** Translator and TTS.  \n- 🏪 Subscription offers **unlimited usage** (no 60-second limit) during the subscription period, available via [![Shopify](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FShopify-7ab55c.svg?style=flat-square&logo=shopify&logoColor=white)](https:\u002F\u002Fr17wvy-t2.myshopify.com).\n  \n\u003C\u002Fdetails>\n\n## 🎥 YouTube Showcase\n\n\u003Ctable style=\"border-collapse: collapse; width: 100%;\">\n  \u003Ctr>\n    \u003Ctd style=\"padding: 10px; border: none;\" align=\"center\">\n      \u003Ca href=\"https:\u002F\u002Fyoutu.be\u002FscC5CicZ6G0\" style=\"text-decoration: none; color: inherit;\">\n        \u003Cimg src=\"https:\u002F\u002Fimg.youtube.com\u002Fvi\u002FscC5CicZ6G0\u002Fhqdefault.jpg\" alt=\"Demo Video 1\" width=\"240\" height=\"135\" style=\"border-radius: 4px;\">\n        \u003Cbr>\n        \u003Cspan style=\"font-size: 16px; font-weight: 600; color: #0f0f0f; line-height: 1.2;\">Demo for Voice-Pro (v2.0)\u003C\u002Fspan>\n      \u003C\u002Fa>\n    \u003C\u002Ftd>\n    \u003Ctd style=\"padding: 10px; border: none;\" align=\"center\">\n      \u003Ca href=\"https:\u002F\u002Fyoutu.be\u002FWfo7vQCD4no\" style=\"text-decoration: none; color: inherit;\">\n        \u003Cimg src=\"https:\u002F\u002Fimg.youtube.com\u002Fvi\u002FWfo7vQCD4no\u002Fhqdefault.jpg\" alt=\"Demo Video 2\" width=\"240\" height=\"135\" style=\"border-radius: 4px;\">\n        \u003Cbr>\n        \u003Cspan style=\"font-size: 16px; font-weight: 600; color: #0f0f0f; line-height: 1.2;\">F5-TTS: Voice Cloning\u003C\u002Fspan>\n      \u003C\u002Fa>\n    \u003C\u002Ftd>\n    \u003Ctd style=\"padding: 10px; border: none;\" align=\"center\">\n      \u003Ca href=\"https:\u002F\u002Fyoutu.be\u002FGOzCDj4MCpo\" style=\"text-decoration: none; color: inherit;\">\n        \u003Cimg src=\"https:\u002F\u002Fimg.youtube.com\u002Fvi\u002FGOzCDj4MCpo\u002Fhqdefault.jpg\" alt=\"Demo Video 3\" width=\"240\" height=\"135\" style=\"border-radius: 4px;\">\n        \u003Cbr>\n        \u003Cspan style=\"font-size: 16px; font-weight: 600; color: #0f0f0f; line-height: 1.2;\">Live Transcription & Translation\u003C\u002Fspan>\n      \u003C\u002Fa>\n    \u003C\u002Ftd>\n    \u003Ctd style=\"padding: 10px; border: none;\" align=\"center\">\n      \u003Ca href=\"https:\u002F\u002Fyoutu.be\u002FYdAq80wjtuQ\" style=\"text-decoration: none; color: inherit;\">\n        \u003Cimg src=\"https:\u002F\u002Fimg.youtube.com\u002Fvi\u002FYdAq80wjtuQ\u002Fhqdefault.jpg\" alt=\"Demo Video 4\" width=\"240\" height=\"135\" style=\"border-radius: 4px;\">\n        \u003Cbr>\n        \u003Cspan style=\"font-size: 16px; font-weight: 600; color: #0f0f0f; line-height: 1.2;\">Multi-Lingual Voice Cloning: Korean - German\u003C\u002Fspan>\n      \u003C\u002Fa>\n    \u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd style=\"padding: 10px; border: none;\" align=\"center\">\n      \u003Ca href=\"https:\u002F\u002Fyoutu.be\u002FTu2okoHY174\" style=\"text-decoration: none; color: inherit;\">\n        \u003Cimg src=\"https:\u002F\u002Fimg.youtube.com\u002Fvi\u002FTu2okoHY174\u002Fhqdefault.jpg\" alt=\"Demo Video 5\" width=\"240\" height=\"135\" style=\"border-radius: 4px;\">\n        \u003Cbr>\n        \u003Cspan style=\"font-size: 16px; font-weight: 600; color: #0f0f0f; line-height: 1.2;\">Multi-Lingual Voice Cloning: English - Korean\u003C\u002Fspan>\n      \u003C\u002Fa>\n    \u003C\u002Ftd>\n    \u003Ctd style=\"padding: 10px; border: none;\" align=\"center\">\n      \u003Ca href=\"https:\u002F\u002Fyoutu.be\u002FdWCEwO56_7Y\" style=\"text-decoration: none; color: inherit;\">\n        \u003Cimg src=\"https:\u002F\u002Fimg.youtube.com\u002Fvi\u002FdWCEwO56_7Y\u002Fhqdefault.jpg\" alt=\"Demo Video 6\" width=\"240\" height=\"135\" style=\"border-radius: 4px;\">\n        \u003Cbr>\n        \u003Cspan style=\"font-size: 16px; font-weight: 600; color: #0f0f0f; line-height: 1.2;\">Multi-Lingual Voice Cloning: Korean - Japanese\u003C\u002Fspan>\n      \u003C\u002Fa>\n    \u003C\u002Ftd>\n    \u003Ctd style=\"padding: 10px; border: none;\" align=\"center\">\n      \u003Ca href=\"https:\u002F\u002Fyoutu.be\u002FHXomwoKS3V4\" style=\"text-decoration: none; color: inherit;\">\n        \u003Cimg src=\"https:\u002F\u002Fimg.youtube.com\u002Fvi\u002FHXomwoKS3V4\u002Fhqdefault.jpg\" alt=\"Demo Video 7\" width=\"240\" height=\"135\" style=\"border-radius: 4px;\">\n        \u003Cbr>\n        \u003Cspan style=\"font-size: 16px; font-weight: 600; color: #0f0f0f; line-height: 1.2;\">NVIDIA RTX Video Super-Resolution\u003C\u002Fspan>\n      \u003C\u002Fa>\n    \u003C\u002Ftd>\n    \u003Ctd style=\"padding: 10px; border: none;\" align=\"center\">\n      \u003Ca href=\"https:\u002F\u002Fyoutu.be\u002FlZK7pLJBHb4\" style=\"text-decoration: none; color: inherit;\">\n        \u003Cimg src=\"https:\u002F\u002Fimg.youtube.com\u002Fvi\u002FlZK7pLJBHb4\u002Fhqdefault.jpg\" alt=\"Demo Video 8\" width=\"240\" height=\"135\" style=\"border-radius: 4px;\">\n        \u003Cbr>\n        \u003Cspan style=\"font-size: 16px; font-weight: 600; color: #0f0f0f; line-height: 1.2;\">AI Karaoke\u003C\u002Fspan>\n      \u003C\u002Fa>\n    \u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd style=\"padding: 10px; border: none;\" align=\"center\">\n      \u003Ca href=\"https:\u002F\u002Fyoutu.be\u002FCo70lh95EsQ\" style=\"text-decoration: none; color: inherit;\">\n        \u003Cimg src=\"https:\u002F\u002Fimg.youtube.com\u002Fvi\u002FCo70lh95EsQ\u002Fhqdefault.jpg\" alt=\"Demo Video 5\" width=\"240\" height=\"135\" style=\"border-radius: 4px;\">\n        \u003Cbr>\n        \u003Cspan style=\"font-size: 16px; font-weight: 600; color: #0f0f0f; line-height: 1.2;\">Multi-Lingual Voice Cloning: English - Korean\u003C\u002Fspan>\n      \u003C\u002Fa>\n    \u003C\u002Ftd>\n  \u003C\u002Ftr>    \n\u003C\u002Ftable>\n\n\n## ⭐ Key Features\n\n### 1. Dubbing Studio\n- YouTube video downloads & audio extraction\n- Voice separation with **Demucs**\n- Supports 100+ languages for speech recognition & translation\n\n### 2. Speech Technologies\n- **Speech-to-Text:** **Whisper**, **Faster-Whisper**, **Whisper-Timestamped**, **WhisperX**\n- **Text-to-Speech:** \n  - **Edge-TTS**: 100+ languages, 400+ voices\n  - **E2-TTS**, **F5-TTS**, **CosyVoice**: Zero-shot cloning\n  - **kokoro**: Ranked #2 in HuggingFace TTS Arena\n\n### 3. Real-Time Translation\n- Instant speech recognition\n- Multilingual translation on the fly\n- Customizable audio inputs\n\n\n## 🤖 WebUI\n\n### `Dubbing Studio` Tab\n- All-in-one hub: YouTube downloads, noise removal, subtitles, translation, & TTS\n- Supports all ffmpeg-compatible formats\n- Output options: WAV, FLAC, MP3\n- Subtitles & recognition for 100+ languages\n- TTS with speed, volume, & pitch controls\n  \n\u003Cp align=\"center\">\n  \u003Cimg style=\"width: 90%; height: 90%\" src=\"docs\u002Fimages\u002Fmain_page.eng.jpg?raw=true\" alt=\"Multilingual Voice Conversion and Subtitle Generation Web UI Interface\"\u002F>\n\u003C\u002Fp>  \n\n\n### `Whisper Caption` Tab\n- Subtitle-focused: 90+ languages\n- Video-integrated subtitle display\n- Word-level highlighting & denoise options\n\n### `Translate` Tab\n- Translation for 100+ languages\n- Supports subtitle files (ASS, SSA, SRT, etc.)\n- Real-time voice recognition & translation\n\n\u003Cp align=\"center\">\n  \u003Cimg style=\"width: 90%; height: 90%\" src=\"docs\u002Fimages\u002Flive_translation_bbc.jpg?raw=true\" alt=\"WebUI for Real-Time Speech Recognition and Translation\"\u002F>\n\u003C\u002Fp>  \n\n### `Speech Generation` Tab\n- Options: **Edge-TTS**, **F5-TTS**, **CosyVoice**, **kokoro**\n- Celeb voice podcasts & multilingual support\n\n\u003Cp align=\"center\">\n  \u003Cimg style=\"width: 90%; height: 90%\" src=\"docs\u002Fimages\u002Ftts_f5_multi.jpg?raw=true\" alt=\"Podcast Production WebUI Using Voice-Cloning Technology\"\u002F>\n\u003C\u002Fp>  \n\n\n\n## 🎤✨ Reference Voice\n\n- Please request the voice you want to add on the Issues page. [Issues](https:\u002F\u002Fgithub.com\u002Fabus-aikorea\u002Fvoice-pro\u002Fissues\u002F50)  \n\n\u003Cdetails>\n\u003Csummary>\nEnglish\n\u003C\u002Fsummary> \u003Cbr \u002F>\n\n\u003Ctable>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FAndrew Bustamante.jpg\" width=\"150\">\u003Cbr>Andrew Bustamante\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FAndrew Huberman.jpg\" width=\"150\">\u003Cbr>Andrew Huberman\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FAvi Loeb.jpg\" width=\"150\">\u003Cbr>Avi Loeb\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FBen Shapiro.jpg\" width=\"150\">\u003Cbr>Ben Shapiro\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FBrett Johnson.jpg\" width=\"150\">\u003Cbr>Brett Johnson\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FBrian Keating.jpg\" width=\"150\">\u003Cbr>Brian Keating\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FCoffeezilla.jpg\" width=\"150\">\u003Cbr>Coffeezilla\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FDan Carlin.jpg\" width=\"150\">\u003Cbr>Dan Carlin\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FDavid Buss.jpg\" width=\"150\">\u003Cbr>David Buss\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FDavid Fravor.jpg\" width=\"150\">\u003Cbr>David Fravor\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FDavid Kipping.jpg\" width=\"150\">\u003Cbr>David Kipping\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FDennis Whyte.jpg\" width=\"150\">\u003Cbr>Dennis Whyte\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FDonald Hoffman.jpg\" width=\"150\">\u003Cbr>Donald Hoffman\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FDonald Trump.jpg\" width=\"150\">\u003Cbr>Donald Trump\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FDouglas Murray.jpg\" width=\"150\">\u003Cbr>Douglas Murray\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FDuncan Trussell.jpg\" width=\"150\">\u003Cbr>Duncan Trussell\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FElon Musk.jpg\" width=\"150\">\u003Cbr>Elon Musk\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FGarry Nolan.jpg\" width=\"150\">\u003Cbr>Garry Nolan\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FJack Barsky.jpg\" width=\"150\">\u003Cbr>Jack Barsky\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FJames Sexton.jpg\" width=\"150\">\u003Cbr>James Sexton\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FJeff Bezos.jpg\" width=\"150\">\u003Cbr>Jeff Bezos\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FJoe Rogan.jpg\" width=\"150\">\u003Cbr>Joe Rogan\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FJohn Mearsheimer.jpg\" width=\"150\">\u003Cbr>John Mearsheimer\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FJordan Peterson.jpg\" width=\"150\">\u003Cbr>Jordan Peterson\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FKanye 'Ye' West.jpg\" width=\"150\">\u003Cbr>Kanye 'Ye' West\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FMark Zuckerberg.jpg\" width=\"150\">\u003Cbr>Mark Zuckerberg\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FMichael Levin.jpg\" width=\"150\">\u003Cbr>Michael Levin\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FMichael Saylor.jpg\" width=\"150\">\u003Cbr>Michael Saylor\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FMichio Kaku.jpg\" width=\"150\">\u003Cbr>Michio Kaku\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FMrBeast.jpg\" width=\"150\">\u003Cbr>MrBeast\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FNick Lane.jpg\" width=\"150\">\u003Cbr>Nick Lane\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FPaul Rosolie.jpg\" width=\"150\">\u003Cbr>Paul Rosolie\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FRyan Graves.jpg\" width=\"150\">\u003Cbr>Ryan Graves\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FSam Altman.jpg\" width=\"150\">\u003Cbr>Sam Altman\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FSam Harris.jpg\" width=\"150\">\u003Cbr>Sam Harris\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FStephen Wolfram.jpg\" width=\"150\">\u003Cbr>Stephen Wolfram\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FTucker Carlson.jpg\" width=\"150\">\u003Cbr>Tucker Carlson\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FVitalik Buterin.jpg\" width=\"150\">\u003Cbr>Vitalik Buterin\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FEnglish\u002FYuval Harari.jpg\" width=\"150\">\u003Cbr>Yuval Harari\u003C\u002Ftd>\n    \u003Ctd>\u003C\u002Ftd>\n    \u003Ctd>\u003C\u002Ftd>\n    \u003Ctd>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n\u003C\u002Ftable>\n\u003C\u002Fdetails>\n\n\n\u003Cdetails>\n\u003Csummary>\nChinese\n\u003C\u002Fsummary> \u003Cbr \u002F>\n\n\u003Ctable>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FChinese\u002FDilraba Dilmurat.jpg\" width=\"150\">\u003Cbr>迪丽热巴 (Dílì Rèbā)\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FChinese\u002FJolin Tsai.jpg\" width=\"150\">\u003Cbr>蔡依林 (Cài Yīlín)\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FChinese\u002FKris Wu.jpg\" width=\"150\">\u003Cbr>吴亦凡 (Wú Yìfán)\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FChinese\u002FLi Yifeng.jpg\" width=\"150\">\u003Cbr>李易峰 (Lǐ Yìfēng)\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FChinese\u002FYang Mi.jpg\" width=\"150\">\u003Cbr>杨幂 (Yáng Mì)\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FChinese\u002FZhao Liying.jpg\" width=\"150\">\u003Cbr>赵丽颖 (Zhào Lìyǐng)\u003C\u002Ftd>\n  \u003C\u002Ftr>\n\u003C\u002Ftable>\n\u003C\u002Fdetails>\n\n\n\u003Cdetails>\n\u003Csummary>\nKorean\n\u003C\u002Fsummary> \u003Cbr \u002F>\n\n\u003Ctable>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FKorean\u002FBTS Jin.jpg\" width=\"150\">\u003Cbr>BTS 진 (Jin)\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FKorean\u002FBTS RM.jpg\" width=\"150\">\u003Cbr>BTS RM\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FKorean\u002FIU.jpg\" width=\"150\">\u003Cbr>IU (아이유)\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FKorean\u002FLeeByungHun.jpg\" width=\"150\">\u003Cbr>이병헌\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FKorean\u002FLeeJungJae.jpg\" width=\"150\">\u003Cbr>이정재\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FKorean\u002FYouJaeSuk.jpg\" width=\"150\">\u003Cbr>유재석\u003C\u002Ftd>\n  \u003C\u002Ftr>\n\u003C\u002Ftable>\n\u003C\u002Fdetails>\n\n\n\u003Cdetails>\n\u003Csummary>\nJapanese\n\u003C\u002Fsummary> \u003Cbr \u002F>\n\n\u003Ctable>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Cimg src=\"celebrities30sREADME\u002FJapanese\u002FAyase Haruka.jpg\" width=\"150\">\u003Cbr>綾瀬はるか (Ayase Haruka)\u003C\u002Ftd>\n    \u003Ctd>\u003C\u002Ftd>\n    \u003Ctd>\u003C\u002Ftd>\n    \u003Ctd>\u003C\u002Ftd>\n    \u003Ctd>\u003C\u002Ftd>\n    \u003Ctd>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n\u003C\u002Ftable>\n\u003C\u002Fdetails>\n\u003Cbr \u002F>\n\n\n## 💻 System Requirements\n- **OS:** Windows 10\u002F11 (64-bit), Linux, Mac\n- **GPU:** NVIDIA with CUDA 12.4 (recommended)\n- **VRAM:** 4GB+ (8GB+ preferred)\n- **RAM:** 4GB+\n- **Storage:** 20GB+ free space\n- **Internet:** Required\n\n\n\n## 📀 Installation\n\nInstall Voice-Pro with ease using **configure.bat** and **start.bat** (use configure.sh and start.sh on Mac\u002FLinux).\n\n\n### 1. Get the Package\n\n  + Clone or download the latest release (**Source code (zip)**) from  [![GitHub Release](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fv\u002Frelease\u002Fabus-aikorea\u002Fvoice-pro)](https:\u002F\u002Fgithub.com\u002Fabus-aikorea\u002Fvoice-pro\u002F)\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002Fabus-aikorea\u002Fvoice-pro.git\n```\n  \n\n### 2. Install & Run\n1. 🚀 **configure.bat**\n   - Sets up git, ffmpeg, and CUDA (if NVIDIA GPU)\n   - Run once; takes 1+ hour with internet\n   - Don’t close the command window\n2. 🚀 **start.bat**\n   - Launches Voice-Pro WebUI\n   - First run installs dependencies (1+ hour)\n   - Retry after deleting **installer_files** if issues arise\n\n### 3. Update\n- 🚀 **update.bat**: Refreshes Python environment (faster than reinstall)\n\n### 4. Uninstall\n- Run **uninstall.bat** or delete the folder (portable install)\n\n\n## ❓Tips & Tricks\n\n#### If Browser does not run automatically\n- Close the Windows-Commnad window and run start.bat again.\n- Run the browser directly and enter the address displayed in the Windows-Command window (e.g. **http:\u002F\u002F127.0.0.1:7870**) in the address bar.\n\n#### If a CUDA Out-Of-Memory error occurs\n- Check the GPU memory status in Windows Task Manager - Performance tab. \n- Set the Denoise level to 0 or 1. Denoise level 2 requires at least 8GB of GPU memory.\n- Set Compute Type to int type. The float type has better quality, but requires more GPU memory.\n\n#### How to improve the quality of subtitles?\n- The quality of subtitles tends to improve with larger Whisper models, but this is not necessarily the case. large > medium > small > base > tiny \n- Among compute types, float type has good performance. The int type is a model that reduces GPU usage and increases speed through model quantization. On the other hand, performance decreases. \n- If you increase the denoise level, more background sounds will be removed, and only the remaining voice will be used for voice recognition. It does not always guarantee good results.\n  \n\n\n## 🚨 Notice\n- Due to [WeConnect](https:\u002F\u002Fwww.wctokyoseoul.com) development work, there will be no Voice-Pro updates for the time being.\n- All Voice-Pro code has been made open source. It is now completely free to use.\n- [WeConnect](https:\u002F\u002Fwww.wctokyoseoul.com) is a communication platform for global cultural exchange.\n\n\n\n\u003Cbr \u002F>\n\n\n## ⏳ SaaS Platforms for Subtitling, Translation, and TTS\n\nThe following table lists SaaS platforms supporting subtitling, translation, and text-to-speech (TTS\u002Fdubbing) functionalities. Costs are calculated for processing a 60-minute Korean video, including subtitle generation, English translation, and English dubbing, based on the latest available pricing data as of April 15, 2025.\n\n| Platform        | Subtitling | Translation | TTS\u002FDubbing | Cost for 60-min Video (USD, Approx.) | Key Features                                                                 |\n|-----------------|------------|-------------|-------------|-------------------------------------|------------------------------------------------------------------------------|\n| **[Maestra](https:\u002F\u002Fmaestra.ai)**     | ✅         | ✅          | ✅          | $23.70                              | 125+ languages, real-time captions, SEO keyword extraction, 15-min free trial. |\n| **[Kapwing](https:\u002F\u002Fwww.kapwing.com)**     | ✅         | ✅          | ✅          | $30~$40 (Pro plan, per minute)     | AI subtitles, 100+ language translations, auto lip-sync dubbing, free tier.   |\n| **[VEED.IO](https:\u002F\u002Fwww.veed.io)**     | ✅         | ✅          | ❌          | $24~$36 (Pro plan, partial)        | 99.9% accurate subtitles, Instagram-optimized captions, intuitive editor.     |\n| **[HappyScribe](https:\u002F\u002Fhappyscribe.com)** | ✅         | ✅          | ✅          | $36~$48 (Pay-as-you-go)            | 120+ languages, professional proofreading, secure, meeting transcription.     |\n| **[Sonix](https:\u002F\u002Fsonix.ai)**       | ✅         | ✅          | ✅          | $30~$40 (Standard plan)            | 54+ languages, 30-min free transcription, YouTube\u002FZoom integration.           |\n| **[Descript](https:\u002F\u002Fdescript.com)**    | ✅         | ✅          | ✅          | $36~$48 (Creator plan)             | Text-based editing, Overdub TTS, filler word removal, 1-hour free transcription. |\n| **[AppTek](https:\u002F\u002Fapptek.ai)**      | ✅         | ✅          | ✅          | Custom pricing (Contact)            | Media-focused, custom models, metadata generation, cloud-based Workbench.     |\n| **[Transkriptor](https:\u002F\u002Ftranskriptor.com)**| ✅         | ✅          | ❌          | $12~$18 (Pay-as-you-go)            | 100+ languages, YouTube link transcription, 99% accuracy, simple editor.      |\n\n### Cost Calculation Details\n- **[Maestra](https:\u002F\u002Fmaestra.ai\u002F)**: Premium Plan ($158\u002Fmonth, 1200 credits). 60-min video: 60 credits (subtitles) + 60 credits (translation) + 60 credits (dubbing) = 180 credits. Cost = (180\u002F1200) * $158 = $23.70.[](https:\u002F\u002Fmaestra.ai\u002Fpricing)\n- **[Kapwing](https:\u002F\u002Fwww.kapwing.com)**: Pro plan (\\~$24\u002Fmonth, limited minutes). Estimated $0.50\\~$0.67\u002Fmin for subtitles+translation+dubbing (based on per-minute pricing trends). 60-min cost: $30\\~$40. Exact pricing requires confirmation.\n- **[VEED.IO](https:\u002F\u002Fwww.veed.io)**: Pro plan (\\~$24\u002Fmonth). Subtitles+translation estimated at $0.40\\~$0.60\u002Fmin. No TTS, so partial processing. 60-min cost: $24\\~$36. Confirm at [veed.io](https:\u002F\u002Fveed.io).\n- **[HappyScribe](https:\u002F\u002Fhappyscribe.com)**: Pay-as-you-go (\\~$0.20\u002Fmin transcription, $0.20\u002Fmin translation, $0.20\u002Fmin dubbing). 60-min cost: $36\\~$48 (assuming combined services). Confirm at [happyscribe.com](https:\u002F\u002Fhappyscribe.com).\n- **[Sonix](https:\u002F\u002Fsonix.ai)**: Standard plan (\\~$10\u002Fhour transcription, additional for translation\u002Fdubbing). Estimated $0.50\\~$0.67\u002Fmin total. 60-min cost: $30\\~$40. Confirm at [sonix.ai](https:\u002F\u002Fsonix.ai).\n- **[Descript](https:\u002F\u002Fdescript.com)**: Creator plan (\\~$24\u002Fmonth, limited hours). Estimated $0.60\\~$0.80\u002Fmin for subtitles+translation+dubbing. 60-min cost: $36\\~$48. Confirm at [descript.com](https:\u002F\u002Fdescript.com).\n- **[AppTek](https:\u002F\u002Fapptek.ai)**: Custom pricing for enterprise. No public per-minute rates. Contact [apptek.ai](https:\u002F\u002Fapptek.ai) for quotes.\n- **[Transkriptor](https:\u002F\u002Ftranskriptor.com)**: Pay-as-you-go ($0.05\\~$0.10\u002Fmin transcription, similar for translation). No TTS, so partial processing. 60-min cost: $12\\~$18. Confirm at [transkriptor.com](https:\u002F\u002Ftranskriptor.com).\n\n### Notes\n- **Cost for 60-min Video**: Costs are approximate and assume processing a 60-minute Korean video for subtitles, English translation, and English dubbing (where available). Platforms without TTS (e.g., VEED.IO, Transkriptor) reflect partial processing costs.\n- **Language Support**: Most platforms support Korean and English. Verify specific language availability on their websites.\n- **Use Cases**:\n  - Media\u002FEntertainment: AppTek, Maestra\n  - Social Media: Kapwing, VEED.IO\n  - Podcasts\u002FInterviews: Sonix, Descript\n  - E-learning\u002FGlobal Content: Transkriptor, HappyScribe\n- **Pricing Updates**: Pricing may vary due to plan changes or promotions. Check official websites for the latest details.\n- For contributions or specific use case recommendations, open an issue or submit a pull request in this repository!\n\n\u003Cbr \u002F>\n\n## ☕ Contributions\n\nHello, I'm David from the Voice-Pro team.\nOur team discovers the best AI technologies in the industry and provides them for anyone to use easily and conveniently.\nWe are a small startup in Korea that has only been around for a year. We are working hard to help you and other creators produce great content.\n\nYour ⭐⭐⭐⭐⭐ review would be greatly appreciated as it helps our business grow with you. Please help support our small team.\n\nThank you,\nABUS Customer Service\n\n- If you want to participate in and help us with this project, feel free to create an [Issues](https:\u002F\u002Fgithub.com\u002Fabus-aikorea\u002Fvoice-pro\u002Fissues) \n- If something goes wrong, please submit a [Pull requests](https:\u002F\u002Fgithub.com\u002Fabus-aikorea\u002Fvoice-pro\u002Fpulls) to improve this project.\n- Any type of contribution is welcome.\n- For inquiries related to purchases, business partnerships, technical tuning, investments, and other matters, please contact us by email. (\u003Cabus.aikorea@gmail.com>).\"\n- If you like this project, please star this repository. We would greatly appreciate it. ⭐⭐⭐\n- You can support Voice-Pro with a donation here:    \n\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fwww.buymeacoffee.com\u002Fabus\">\n  \u003Cimg src=\"https:\u002F\u002Fwww.buymeacoffee.com\u002Fassets\u002Fimg\u002Fcustom_images\u002Forange_img.png\" alt=\"Buy Me a Coffee\" style=\"height: 20px;\">\n\u003C\u002Fa>\n\n\n\n## 📬 Contact\n- Email: \u003Cabus.aikorea@gmail.com>\n- Homepage (Korean): \u003Chttps:\u002F\u002Fwww.wctokyoseoul.com>\n- Paid Version Purchase: [Shopify (Global)](https:\u002F\u002Fr17wvy-t2.myshopify.com), [Naver (Korean)](https:\u002F\u002Fsmartstore.naver.com\u002Fabus)\n\n## 🙏 Credits\n* Demucs: \u003Chttps:\u002F\u002Fgithub.com\u002Ffacebookresearch\u002Fdemucs>\n* yt-dlp: \u003Chttps:\u002F\u002Fgithub.com\u002Fyt-dlp\u002Fyt-dlp>\n* gradio: \u003Chttps:\u002F\u002Fgithub.com\u002Fgradio-app\u002Fgradio>\n* edge-TTS: \u003Chttps:\u002F\u002Fgithub.com\u002Frany2\u002Fedge-tts>\n* F5-TTS: \u003Chttps:\u002F\u002Fgithub.com\u002FSWivid\u002FF5-TTS.git>\n* openai-whisper: \u003Chttps:\u002F\u002Fgithub.com\u002Fopenai\u002Fwhisper>\n* faster-whisper: \u003Chttps:\u002F\u002Fgithub.com\u002FSYSTRAN\u002Ffaster-whisper>\n* whisper-timestamped: \u003Chttps:\u002F\u002Fgithub.com\u002Flinto-ai\u002Fwhisper-timestamped>\n* whisperX: \u003Chttps:\u002F\u002Fgithub.com\u002Fm-bain\u002FwhisperX>\n* CosyVoice: \u003Chttps:\u002F\u002Fgithub.com\u002FFunAudioLLM\u002FCosyVoice>\n* kokoro: \u003Chttps:\u002F\u002Fgithub.com\u002Fhexgrad\u002Fkokoro>\n* Deep-Translator: \u003Chttps:\u002F\u002Fgithub.com\u002Fnidhaloff\u002Fdeep-translator>\n* spaCy: \u003Chttps:\u002F\u002Fgithub.com\u002Fexplosion\u002FspaCy>\n\n\n\n## ©️ Copyright\n  \u003Cimg src=\"docs\u002Fimages\u002FABUS-logo.jpg\" width=\"100\" height=\"100\"> by [ABUS](https:\u002F\u002Fwww.wctokyoseoul.com)\n\n","Voice-Pro 是一个基于 AI 的 Web 应用程序，用于语音识别、翻译和多语言配音。其核心功能包括文本转语音（TTS）、零样本语音克隆（E2 & F5-TTS, CosyVoice）、Whisper 音频处理、YouTube 视频下载、Demucs 人声分离以及多语言翻译。该工具使用了先进的技术栈如 Whisper、Edge-TTS 和 Gradio 等，支持 CUDA 加速以提高性能。Voice-Pro 适用于需要处理 YouTube 视频、生成字幕、进行语音到文本转换及多语言配音的场景，是创作者和开发者理想的多媒体处理工具。",2,"2026-06-11 03:39:44","high_star"]